crop_image

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are supplied, so the description carries the full behavioral burden. It never says that cropping discards pixels outside the rectangle, whether the operation is undoable, or what happens if only some of x/y/width/height are provided. For a destructive canvas mutation with zero annotation coverage, this is a substantial gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single well-formed sentence with the primary behavior front-loaded and the fallback clause second. Nothing is wasted and nothing is buried.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no annotations, no output schema, and four completely undocumented parameters, the description should explain coordinate semantics and the destructive nature of the operation. It covers the high-level intent but leaves an agent unable to call it correctly with confidence.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the four parameters (x, y, width, height) are documented nowhere. The description only alludes to a 'rectangle' without specifying coordinate origin, units, whether all four must be supplied together, or how partial values are handled.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description gives a specific verb (crop) and resource (the canvas), plus the two modes of operation: an explicit rectangle or the current selection's bounds. It implicitly distinguishes itself from siblings like resize_canvas and scale_image, which change dimensions rather than discarding pixels, though it never names them.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It states the fallback condition clearly: with no rectangle, the selection bounds are used. That is a real usage rule, but there is no guidance on when to prefer crop over resize_canvas or scale_image, and no mention of prerequisites such as an active selection being required for the fallback path.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.